coze-dev / coze-dev/coze-studio

知识库默认分段效果,本地和官网有差异

Open
#2,158 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
TypeScript
Stars
21.6k
Forks
3.1k
PR merge metrics
No merged PRs in 30d

Description

本地配置了paddleocr,在文档解析策略将三个全选后点击下一步,展示的分段效果没有官网效果好,有的表格内容没有识别到。请问这是什么原因呢,有改进方法吗。

配置:
文档解析器配置了:PP-StructureV3
OCR配置了:paddleocr
向量模型:Qwen3-embedding-8B

附件是本地和官网的分段结果截图和原始文件

Image
Image
Image

[HSK标准教程 1 教师用书 【ISBN号】9787561939994_13797038_部分8-12.pdf](https://github.com/user-attachments/files/22289247/HSK.1.ISBN.9787561939994_13797038_.8-12.pdf)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.